| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0198675496688743, | |
| "eval_steps": 8, | |
| "global_step": 38, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.026490066225165563, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1.0781, | |
| "eval_samples_per_second": 14.841, | |
| "eval_steps_per_second": 7.421, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.13245033112582782, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.2119205298013245, | |
| "eval_loss": NaN, | |
| "eval_runtime": 0.6857, | |
| "eval_samples_per_second": 23.335, | |
| "eval_steps_per_second": 11.668, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.26490066225165565, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.3973509933774834, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.233620996141421e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.423841059602649, | |
| "eval_loss": NaN, | |
| "eval_runtime": 0.6931, | |
| "eval_samples_per_second": 23.085, | |
| "eval_steps_per_second": 11.542, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.5298013245033113, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.169418695587791e-05, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.6357615894039735, | |
| "eval_loss": NaN, | |
| "eval_runtime": 0.712, | |
| "eval_samples_per_second": 22.473, | |
| "eval_steps_per_second": 11.236, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.6622516556291391, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.4401776194834613e-05, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.7947019867549668, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.8825509907063327e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.847682119205298, | |
| "eval_loss": NaN, | |
| "eval_runtime": 0.695, | |
| "eval_samples_per_second": 23.022, | |
| "eval_steps_per_second": 11.511, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.9271523178807947, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.8058334845816213e-06, | |
| "loss": 0.0, | |
| "step": 35 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 38, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1370160142221312.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |